def plot_comps(N, S):
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
for j in range(100):
# Random composition
RAD = RandCompFast(N, S)
ranks = range(1, len(RAD)+1)
plt.plot(ranks, RAD, lw = 1, c='gray')
# Predicted geometric series
predRAD = predRADs.get_GeomSeries(N, S, False)
ranks = range(1, S+1)
plt.plot(ranks, predRAD, lw = 2, c='Lime')
plt.yscale('log')
plt.ylabel('Abundance')
plt.xlabel('Rank in abundance')
plt.title('Smallest abundance of MaxEnt prediction for SAD constrained\nby N and S (Geometric Series):'+str(min(predRAD)))
plt.show()
return
def plot_RADs_canonical(N, S):
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
# Predicted geometric series
predRAD = predRADs.get_GeomSeries(N, S, False) # False mean no zeros allowed
ranks = range(1, S+1)
plt.plot(ranks, predRAD, lw = 1, c='m')
# Predicted log-series
logSeries = mete.get_mete_rad(S, N)
predRAD = logSeries[0]
ranks = range(1, S+1)
plt.plot(ranks, predRAD, lw = 1, c='c')
# Predicted PLN
#predRAD = pln.get_rad_from_obs(predRAD, 'pln')
#ranks = range(1, len(predRAD)+1)
#plt.plot(ranks, predRAD, lw = 1, c='gray')
plt.yscale('log')
plt.show()
return
def getPredRADs(N, S, Nmax):
PRED = []
# Predicted geometric series
predRAD = predRADs.get_GeomSeries(N, S, False) # False mean no zeros allowed
PRED.append(predRAD)
# Predicted log-series
logSeries = mete.get_mete_rad(S, N)
predRAD = logSeries[0]
PRED.append(predRAD)
# Predicted PLN
predRAD = pln.get_rad_from_obs(RAD, 'pln')
PRED.append(predRAD)
sample_size = 10
# Predicted from compositions (basically geometric series)
predRAD = getPred(N, S, maxn, 'compositions', sample_size)
PRED.append(predRAD)
# Predicted from Fraction 1: Power Fraction
predRAD = getPred(N, S, maxn, 'power fraction', sample_size)
PRED.append(predRAD)
# Predicted from Fraction 2: Random non-preemption
predRAD = getPred(N, S, maxn, 'random fraction non-preemption', sample_size)
PRED.append(predRAD)
# Predicted from Fraction 3: Random preemption
predRAD = getPred(N, S, maxn, 'random fraction', sample_size)
PRED.append(predRAD)
return PRED
def generate_obs_pred_data(datasets, methods):
for method in methods:
for dataset in datasets:
gN = 0
#OUT = open(mydir+'/data/'+method+'_'+dataset+'_obs_pred.txt','w+')
IN = mydir+'/MicroMETE/data/'+dataset+'_SADs.txt'
num_lines = sum(1 for line in open(IN))
for line in open(IN):
line = line.split()
obs = map(int, line)
obs = list([x for x in obs if x > 1])
N = sum(obs)
gN += N
print N
S = len(obs)
if S < 10:
continue
obs.sort()
obs.reverse()
print method, dataset, N, S, 'countdown:', num_lines,
if method == 'geom': # Predicted geometric series
pred = predRADs.get_GeomSeries(N, S, False) # False mean no zeros allowed
elif method == 'mete': # Predicted log-series
logSeries = mete.get_mete_rad(S, N)
pred = logSeries[0]
r2 = macroecotools.obs_pred_rsquare(np.log10(obs), np.log10(pred))
print " r2:", r2
# write to file, by cite, observed and expected ranked abundances
#for i, sp in enumerate(pred):
# print>> OUT, obs[i], pred[i]
num_lines -= 1
print 'N(HMP): ',gN
#OUT.close()
print dataset
